# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

## Standard search crawlers (Googlebot, Bingbot, etc.)
User-agent: *
Allow: /
Disallow: /admin/

## AI training crawlers -- opt out
## These respect robots.txt for training opt-out per each vendor's published
## documentation. Mirror policy in /ai.txt. Pre-existing copyright applies.

# OpenAI training
User-agent: GPTBot
Disallow: /

# Anthropic training (current + legacy)
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# Google Gemini training opt-out signal
User-agent: Google-Extended
Disallow: /

# Apple Intelligence training opt-out signal
User-agent: Applebot-Extended
Disallow: /

# Common Crawl (frequent training corpus source)
User-agent: CCBot
Disallow: /

# ByteDance / TikTok training
User-agent: Bytespider
Disallow: /

# Meta training crawlers
User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

# Cohere training
User-agent: cohere-ai
Disallow: /

# Webz.io / Omgili (often resold as training data)
User-agent: omgili
Disallow: /

# Amazon
User-agent: Amazonbot
Disallow: /

## AI search / citation crawlers (user-triggered fetches, not training) -- allow

# OpenAI search + user-triggered fetch
User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic search + user-triggered fetch
User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Perplexity citations
User-agent: PerplexityBot
Allow: /

Sitemap: https://screenfine.info/sitemap-index.xml
Sitemap: https://screenfine.info/sitemap-posts.xml